inference/research
verifiedhigh · 0.95updated 2026-10-03

Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity

paper

Fields

id
sources/pap-arch-2101-03961
URL
https://arxiv.org/abs/2101.03961
Publisher
arXiv
Kind
paper
Published
2021-01-11
Accessed
2026-10-03
notes
Published in Journal of Machine Learning Research (JMLR) 2022; arXiv v3 revised 2022-06-16. Confirmed via arXiv abs page and Semantic Scholar (venue 'Journal of machine learning research').

Notes

Published in Journal of Machine Learning Research (JMLR) 2022; arXiv v3 revised 2022-06-16. Confirmed via arXiv abs page and Semantic Scholar (venue 'Journal of machine learning research').

Cross-references

This record references no other records.